Extracting Entities from Legal Texts

[yangxue-1]

Is there an existing issue for this?

• [ ] I have searched the existing issues
• [ ] I have checked #657 to validate if my issue is covered by community support

Describe the issue

Function: Questions and Answers Based on Chinese Legal Provisions Model: based on qwen2:7b Problem: The entities extracted from legal provisions are not accurate and comprehensive enough. How to optimize the extraction?

Steps to reproduce

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Additional Information

• GraphRAG Version:0.1.1
• Operating System:ubuntu 22.04
• Python Version:3.10
• Related Issues:qwen2:7b

[KylinMountain]

You can check my article about how to prompt and adjust the prompt in manually.

GraphRAG失效？快用Prompt Tune适配文档的领域和语言 and the other article about adjust the entity to what you want in my wechat 公众号。

[yangxue-1]

You can check my article about how to prompt and adjust the prompt in manually.

GraphRAG失效？快用Prompt Tune适配文档的领域和语言 and the other article about adjust the entity to what you want in my wechat 公众号。

好的，我学习一下，非常感谢

[natoverse]

I also suggest trying the auto-tuning function to tailor your entity extraction prompts to the specifics of your data domain before running ingest.

[yangxue-1]

I also suggest trying the auto-tuning function to tailor your entity extraction prompts to the specifics of your data domain before running ingest.

Ok,thanks very much.